INDEX

Explanations

large numbers in the text

oai_token-act-pair · gpt-3.5-turbo

mentions of large numbers, particularly in the context of quantities or statistics

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

itiz

-0.77

abus

-0.76

 tremend

-0.72

alys

-0.72

nect

-0.71

krit

-0.69

warts

-0.69

nam

-0.69

ufact

-0.69

notation

-0.68

POSITIVE LOGITS

0.98

lbs

0.96

 hectares

0.94

 pounds

0.94

lb

0.91

 acres

0.90

gp

0.90

yen

0.87

IU

0.87

sq

0.87

Activations Density 0.070%

large numbers in the text

mentions of large numbers, particularly in the context of quantities or statistics

No Comments

No Known Activations